Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4502 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8239. Min Range: -6.8239
Max Act: 6.8239. Min Act: -0.1700
Data Index: 2334456 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8239. Min Range: -6.8239
Max Act: 6.7927. Min Act: -0.1700
Data Index: 1958978 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8239. Min Range: -6.8239
Max Act: 6.7302. Min Act: -0.1700
Data Index: 5440332 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8239. Min Range: -6.8239
Max Act: 6.6989. Min Act: -0.1700
Data Index: 1181027 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8239. Min Range: -6.8239
Max Act: 6.5739. Min Act: -0.1700
Data Index: 5303087 (Open Web Text)
Max Activating Token Index: 579
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8239. Min Range: -6.8239
Max Act: 6.5427. Min Act: -0.1700
Data Index: 5756996 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8239. Min Range: -6.8239
Max Act: 6.5427. Min Act: -0.1700
Data Index: 5370195 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8239. Min Range: -6.8239
Max Act: 6.5114. Min Act: -0.1700
Data Index: 1402481 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8239. Min Range: -6.8239
Max Act: 6.4802. Min Act: -0.1700
Data Index: 4913769 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8239. Min Range: -6.8239
Max Act: 6.4802. Min Act: -0.1700
Data Index: 7617697 (Open Web Text)
Max Activating Token Index: 277
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8239. Min Range: -6.8239
Max Act: 6.4489. Min Act: -0.1700
Data Index: 2872116 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8239. Min Range: -6.8239
Max Act: 6.4177. Min Act: -0.1700
Data Index: 7517309 (Open Web Text)
Max Activating Token Index: 84
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8239. Min Range: -6.8239
Max Act: 6.3864. Min Act: -0.1700
Data Index: 3793060 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8239. Min Range: -6.8239
Max Act: 6.3552. Min Act: -0.1700
Data Index: 4977865 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8239. Min Range: -6.8239
Max Act: 6.3864. Min Act: -0.1700
Data Index: 6593438 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8239. Min Range: -6.8239
Max Act: 6.3864. Min Act: -0.1700
Data Index: 6699474 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8239. Min Range: -6.8239
Max Act: 6.3864. Min Act: -0.1700
Data Index: 4355766 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8239. Min Range: -6.8239
Max Act: 6.3552. Min Act: -0.1700
Data Index: 809039 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8239. Min Range: -6.8239
Max Act: 6.3239. Min Act: -0.1700
Data Index: 3895337 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8239. Min Range: -6.8239
Max Act: 6.3239. Min Act: -0.1700
Data Index: 7312995 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #19